Disney Research Studios

We present comprehensive comparisons with commercial software packages and relevant methods in literature, which show that the quality of our results is superior to any other currently available green-screen keying solution.

We propose a method to generate an accurate point-based projection with such devices.

In this paper, we present a modified algorithm which builds upon the previous work by redesigning key components to achieve real-time performance.

We present a novel phase-based method for propagating modifications of one video frame to an entire sequence.

We present a generic latency measurement device which can be used to accurately measure the overall end-to-end latency of camera-based AR systems with an accuracy below one millisecond.

We present an algorithm to balance 3D printed models using movable embedded masses. As input, the user provides a 3D model together with the desired suspension, standing, and immersion objectives.

We present a new benchmark dataset and evaluation methodology for the area of video object segmentation

We propose a novel approach to video segmentation that operates in bilateral space.

We present CANVAS, a computer-assisted visual authoring tool for synthesizing multi-character animations from sparsely-specified narrative events.

We consider three foveated rendering methods and propose practical rules of thumb for each method to achieve significant performance gains in real-time rendering frameworks.